Typhoon2-Audio

Parameters

9.7B

Published

Dec 19, 2024

Typhoon2-Audio is an AI model developed by Typhoon / SCB 10X (Thailand), first published in December 2024. It works in the audio, language, speech and multimodal domain, on tasks such as language modeling/generation, speech synthesis, speech recognition (asr) and 5 more.

Epoch AI has no training-compute estimate for this model. The model has 9,688,000,000 parameters.

Access: Open weights (restricted use). Its weights are openly available. It is built on top of Llama 3.1 Typhoon 2 8B. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Typhoon / SCB 10X
Country of organization: Thailand
Domain: Audio, Language, Speech, Multimodal
Task: Language modeling/generation, Speech synthesis, Speech recognition (ASR), Text-to-speech (TTS), Audio generation, Audio question answering, Translation, Speech-to-speech
Parameters: 9,688,000,000
Model accessibility: Open weights (restricted use)
Open weights: Yes
Base model: Llama 3.1 Typhoon 2 8B
Epoch confidence: Confident